Automated Machine Learning, Bounded Rationality, and Rational Metareasoning

TL;DR

This paper explores how bounded rationality principles apply to automated machine learning (AutoML), viewing AutoML as an agent making meta-level decisions to optimize model training within resource constraints.

Contribution

It introduces a perspective that frames AutoML as a bounded rational agent engaging in meta-reasoning to efficiently allocate limited computational resources.

Findings

AutoML can be modeled as a bounded rational agent.

Meta-reasoning improves AutoML efficiency.

Resource-aware AutoML strategies are effective.

Abstract

The notion of bounded rationality originated from the insight that perfectly rational behavior cannot be realized by agents with limited cognitive or computational resources. Research on bounded rationality, mainly initiated by Herbert Simon, has a longstanding tradition in economics and the social sciences, but also plays a major role in modern AI and intelligent agent design. Taking actions under bounded resources requires an agent to reflect on how to use these resources in an optimal way - hence, to reason and make decisions on a meta-level. In this paper, we will look at automated machine learning (AutoML) and related problems from the perspective of bounded rationality, essentially viewing an AutoML tool as an agent that has to train a model on a given set of data, and the search for a good way of doing so (a suitable "ML pipeline") as deliberation on a meta-level.